Open access
2026
E2AM: A Controlled Evaluation Framework for Energy-Aware Training and Deployment of Deep Vision Models
E2AM is presented, a controlled, hardware-measured framework for evaluating five training-time interventions—tensor caching, AMP, gradient accumulation, sparsity regularization, and cosine learning-rate scheduling—together with an energy-aware early-stopping rule and contributes a controlled evaluation methodology for...
Satyanarayana Kanulla, E. S. Reddy, Shanmukesh Bonala
· IEEE Access · 0 citations